{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T17:33:38Z","timestamp":1790012018651,"version":"4.0.1"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T00:00:00Z","timestamp":1665792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T00:00:00Z","timestamp":1665792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Ministry of Electronics and Information Technology, Government of India"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-022-01414-4","type":"journal-article","created":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T14:02:41Z","timestamp":1665842561000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Document Image Analysis Using Deep Multi-modular Features"],"prefix":"10.1007","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5615-7803","authenticated-orcid":false,"given":"K. V.","family":"Jobin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajoy","family":"Mondal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C. V.","family":"Jawahar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,15]]},"reference":[{"key":"1414_CR1","doi-asserted-by":"crossref","unstructured":"Das A, Roy S, Bhattacharya U, Parui SK. Document image classification with intra-domain transfer learning and stacked generalization of deep convolutional neural networks. In: ICPR 2018.","DOI":"10.1109\/ICPR.2018.8545630"},{"key":"1414_CR2","doi-asserted-by":"crossref","unstructured":"Afzal MZ, Kolsch A, Ahmed S, Liwicki M. Cutting the error by half investigation of very deep cnn and advanced training strategies for document image classification. In: ICDAR 2017.","DOI":"10.1109\/ICDAR.2017.149"},{"key":"1414_CR3","doi-asserted-by":"crossref","unstructured":"Jobin K, Mondal A, Jawahar C. Docfigure: a dataset for scientific document figure classification. In: GREC 2019.","DOI":"10.1109\/ICDARW.2019.00018"},{"key":"1414_CR4","doi-asserted-by":"crossref","unstructured":"Ubul K, Tursun G, Aysa A, Impedovo D, Pirlo G, Yibulayin T. Script identification of multi-script documents: a survey. IEEE Access. 2017.","DOI":"10.1109\/ACCESS.2017.2689159"},{"key":"1414_CR5","doi-asserted-by":"crossref","unstructured":"Torkkola K. Discriminative features for text document classification. Formal Pattern Anal Appl. 2004;6(4):301\u20138.","DOI":"10.1007\/s10044-003-0196-8"},{"key":"1414_CR6","doi-asserted-by":"crossref","unstructured":"Jiang H, Pan Z, Hu P. Discriminative learning of generative models: large margin multinomial mixture models for document classification. Pattern Anal Appl. 2015;18(3):535\u201351","DOI":"10.1007\/s10044-014-0382-x"},{"key":"1414_CR7","doi-asserted-by":"crossref","unstructured":"Soleimani H, Miller DJ. Exploiting the value of class labels on high-dimensional feature spaces: topic models for semi-supervised document classification. Pattern Anal Appl. 2019;22(2):299\u2013309","DOI":"10.1007\/s10044-017-0629-4"},{"key":"1414_CR8","unstructured":"Iwana BK, Rizvi STR, Ahmed S, Dengel A, Uchida S. Judging a book by its cover. 2016."},{"key":"1414_CR9","doi-asserted-by":"crossref","unstructured":"Singh AK, Mishra A, Dabral P, Jawahar CV. A simple and effective solution for script identification in the wild. Pattern Recognit. 2016. p. 428\u201333","DOI":"10.1109\/DAS.2016.57"},{"key":"1414_CR10","doi-asserted-by":"crossref","unstructured":"Shi B, Bai X, Yao C. Script identification in the wild via discriminative convolutional neural network. Pattern Recognit. 2016;52:448\u201358","DOI":"10.1016\/j.patcog.2015.11.005"},{"key":"1414_CR11","doi-asserted-by":"crossref","unstructured":"Liu L, Wang Z, Qiu T, Chen Q, Lu Y, Suen CY. Document image classification: progress over two decades. Neurocomputing. 2021;453:223\u201340.","DOI":"10.1016\/j.neucom.2021.04.114"},{"key":"1414_CR12","doi-asserted-by":"crossref","unstructured":"Harley AW, Ufkes A, Derpanis KG. Evaluation of deep convolutional nets for document image classification and retrieval. In: ICDAR 2015.","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"1414_CR13","doi-asserted-by":"crossref","unstructured":"Tensmeyer C, Martinez T. Analysis of convolutional neural networks for document image classification. In: ICDAR 2017.","DOI":"10.1109\/ICDAR.2017.71"},{"key":"1414_CR14","unstructured":"Csurka G, Larlus D, Gordo A, Almazan J. What is the right way to represent document images? 2016."},{"key":"1414_CR15","doi-asserted-by":"crossref","unstructured":"Wang Y, Morariu VI, Davis LS. Learning a discriminative filter bank within a cnn for fine-grained recognition. In: CVPR 2018.","DOI":"10.1109\/CVPR.2018.00436"},{"key":"1414_CR16","doi-asserted-by":"crossref","unstructured":"Zheng H, Fu J, Zha Z-J, Luo J. Looking for the devil in the details: learning trilinear attention sampling network for fine-grained image recognition. In: CVPR 2019.","DOI":"10.1109\/CVPR.2019.00515"},{"key":"1414_CR17","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi AA. Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence 2017.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1414_CR18","doi-asserted-by":"crossref","unstructured":"Sarkhel R, Nandi A. Deterministic routing between layout abstractions for multi-scale classification of visually rich documents. In: IJCAI 2019.","DOI":"10.24963\/ijcai.2019\/466"},{"key":"1414_CR19","doi-asserted-by":"crossref","unstructured":"Xu Y, Li M, Cui L, Huang S, Wei F, Zhou M. Layoutlm: pre-training of text and layout for document image understanding. In: ACM SIGKDD international conference on knowledge discovery & data mining 2020.","DOI":"10.1145\/3394486.3403172"},{"key":"1414_CR20","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K. Bert: Pre-training of deep bidirectional transformers for language understanding. 2018."},{"key":"1414_CR21","unstructured":"Dauphinee T, Patel N, Rashidi M. Modular multimodal architecture for document classification. 2019."},{"key":"1414_CR22","doi-asserted-by":"crossref","unstructured":"Appalaraju S, Jasani B, Kota BU, Xie Y, Manmatha R. Docformer: end-to-end transformer for document understanding. In: ICCV 2021.","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"1414_CR23","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In: NIPS; 2012. p. 1097\u2013105."},{"key":"1414_CR24","doi-asserted-by":"crossref","unstructured":"Zujovic J, Gandy L, Friedman S, Pardo B, Pappas TN. Classifying paintings by artistic genre: an analysis of features & classifiers. In: International workshop on multimedia signal processing 2009.","DOI":"10.1109\/MMSP.2009.5293271"},{"key":"1414_CR25","unstructured":"Chiang H, Ge Y, Wu C. Classification of book genres by cover and title. Computer science: class report; 2015."},{"key":"1414_CR26","doi-asserted-by":"crossref","unstructured":"Biradar GR, Raagini J, Varier A, Sudhir M. Classification of book genres using book cover and title. In: International conference on intelligent systems and green technology (ICISGT) 2019.","DOI":"10.1109\/ICISGT44072.2019.00031"},{"key":"1414_CR27","doi-asserted-by":"crossref","unstructured":"Lucieri A, Sabir H, Siddiqui SA, Rizvi STR, Iwana BK, Uchida S, Dengel A, Ahmed S. Benchmarking deep learning models for classification of book covers. SN computer science 2020.","DOI":"10.1007\/s42979-020-00132-z"},{"key":"1414_CR28","doi-asserted-by":"crossref","unstructured":"Liu Y, Lu X, Qin Y, Tang Z, Xu J. Review of chart recognition in document images. In: VDA 2013.","DOI":"10.1117\/12.2008467"},{"key":"1414_CR29","unstructured":"Zhou YP, Tan CL. Hough technique for bar charts detection and recognition in document images. In: ICIP 2000."},{"key":"1414_CR30","doi-asserted-by":"crossref","unstructured":"Zhou YP, Tan CL. Bar charts recognition using hough based syntactic segmentation. In: ICTAD 2000.","DOI":"10.1007\/3-540-44590-0_45"},{"key":"1414_CR31","unstructured":"Zhou Y, Tan CL. Learning-based scientific chart recognition. In: IWGR 2001."},{"key":"1414_CR32","doi-asserted-by":"crossref","unstructured":"Prasad VSN, Siddiquie B, Golbeck J, Davis LS. Classifying computer generated charts. In: CBMI 2007.","DOI":"10.1109\/CBMI.2007.385396"},{"key":"1414_CR33","doi-asserted-by":"crossref","unstructured":"Savva M, Kong N, Chhajta A, Fei-Fei L, Agrawala M, Heer J. Revision: automated classification, analysis and redesign of chart images. In: User interface software and technology 2011.","DOI":"10.1145\/2047196.2047247"},{"key":"1414_CR34","doi-asserted-by":"crossref","unstructured":"Kavasidis I, Palazzo S, Spampinato C, Pino C, Giordano D, Giuffrida D, Messina P. A saliency-based convolutional neural network for table and chart detection in digitized documents. 2018.","DOI":"10.1007\/978-3-030-30645-8_27"},{"key":"1414_CR35","doi-asserted-by":"crossref","unstructured":"Tang B, Liu X, Lei J, Song M, Tao D, Sun S, Dong F. Deepchart: combining deep convolutional networks and deep belief networks in chart classification. Signal Process. 2016.","DOI":"10.1016\/j.sigpro.2015.09.027"},{"key":"1414_CR36","doi-asserted-by":"crossref","unstructured":"Siegel N, Horvitz Z, Levin R, Divvala S, Farhadi A. Figureseer: parsing result-figures in research papers. In: ECCV 2016.","DOI":"10.1007\/978-3-319-46478-7_41"},{"key":"1414_CR37","doi-asserted-by":"crossref","unstructured":"Aletras N, Mittal A. Labeling topics with images using a neural network. In: European conference on information retrieval 2017.","DOI":"10.1007\/978-3-319-56608-5_40"},{"key":"1414_CR38","doi-asserted-by":"crossref","unstructured":"Charbonnier J, Sohmen L, Rothman J, Rohden B, Wartena C. Noa: a search engine for reusable scientific images beyond the life sciences. In: European conference on information retrieval 2018.","DOI":"10.1007\/978-3-319-76941-7_78"},{"key":"1414_CR39","unstructured":"Shijian L, Tan CL. Script and language identification in noisy and degraded document images. In: IEEE Transactions on PAMI 2007."},{"key":"1414_CR40","doi-asserted-by":"crossref","unstructured":"Zhou L, Lu Y, Tan CL. Bangla\/English script identification based on analysis of connected component profiles. In: International workshop on document analysis systems 2006.","DOI":"10.1007\/11669487_22"},{"key":"1414_CR41","doi-asserted-by":"crossref","unstructured":"Sharma N, Pal U, Blumenstein M. A study on word-level multi-script identification from video frames. In: 2014 international joint conference on neural networks (IJCNN) 2014.","DOI":"10.1109\/IJCNN.2014.6889906"},{"key":"1414_CR42","unstructured":"Mei J, Dai L, Shi B, Bai X. Scene text script identification with convolutional recurrent neural networks. In: ICPR 2016."},{"key":"1414_CR43","doi-asserted-by":"crossref","unstructured":"Lu L, Yi Y, Huang F, Wang K, Wang Q. Integrating local cnn and global cnn for script identification in natural scene images. IEEE Access. 2019;7:52669\u201379.","DOI":"10.1109\/ACCESS.2019.2911964"},{"key":"1414_CR44","doi-asserted-by":"crossref","unstructured":"Bhunia AK, Konwer A, Bhunia AK, Bhowmick A, Roy PP, Pal U. Script identification in natural scene image and video frames using an attention based convolutional-LSTM network. Pattern Recognit. 2019;85:172\u201384.","DOI":"10.1016\/j.patcog.2018.07.034"},{"key":"1414_CR45","doi-asserted-by":"crossref","unstructured":"Ghosh M, Mukherjee H, Obaidullah SM, Santosh K, Das N, Roy K. Lwsinet: a deep learning-based approach towards video script identification. Multim Tools Appl. 2021;80(19):29095\u2013128.","DOI":"10.1007\/s11042-021-11103-8"},{"key":"1414_CR46","doi-asserted-by":"crossref","unstructured":"Chatfield K, Simonyan K, Vedaldi A, Zisserman A. Return of the devil in the details: delving deep into convolutional nets 2014. arXiv:1405.3531","DOI":"10.5244\/C.28.6"},{"key":"1414_CR47","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014."},{"key":"1414_CR48","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: CVPR 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1414_CR49","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: CVPR 2016.","DOI":"10.1109\/CVPR.2016.308"},{"key":"1414_CR50","doi-asserted-by":"crossref","unstructured":"Cimpoi M, Maji S, Vedaldi A. Deep filter banks for texture recognition and segmentation. In: CVPR 2015.","DOI":"10.1109\/CVPR.2015.7299007"},{"key":"1414_CR51","doi-asserted-by":"crossref","unstructured":"Zhang H, Xue J, Dana K. Deep ten: texture encoding network. In: CVPR 2017.","DOI":"10.1109\/CVPR.2017.309"},{"key":"1414_CR52","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J. Pyramid scene parsing network. In: CVPR 2017.","DOI":"10.1109\/CVPR.2017.660"},{"key":"1414_CR53","unstructured":"Loshchilov I, Hutter F. Sgdr: stochastic gradient descent with warm restarts. 2016."},{"key":"1414_CR54","doi-asserted-by":"crossref","unstructured":"Li P, Gu J, Kuen J, Morariu VI, Zhao H, Jain R, Manjunatha V, Liu H. Selfdoc: self-supervised document representation learning. In: CVPR 2021.","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"1414_CR55","unstructured":"Bao H, Dong L, Wei F, Wang W, Yang N, Liu X, Wang Y, Gao J, Piao S, Zhou M, et\u00a0al. Unilmv2: Pseudo-masked language models for unified language model pre-training. In: International conference on machine learning 2020. PMLR."},{"key":"1414_CR56","doi-asserted-by":"crossref","unstructured":"Xu Y, Xu Y, Lv T, Cui L, Wei F, Wang G, Lu Y, Florencio D, Zhang C, Che W, et al. Layoutlmv2: multi-modal pre-training for visually-rich document understanding. 2020.","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"1414_CR57","doi-asserted-by":"crossref","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P, et al. Gradient-based learning applied to document recognition. In: Proceedings of the IEEE. 1998.","DOI":"10.1109\/5.726791"},{"key":"1414_CR58","doi-asserted-by":"crossref","unstructured":"Tang B, Liu X, Lei J, Song M, Tao D, Sun S, Dong F. Deepchart: combining deep convolutional networks and deep belief networks in chart classification. Signal Process. 2016;124:156\u201361.","DOI":"10.1016\/j.sigpro.2015.09.027"},{"key":"1414_CR59","doi-asserted-by":"crossref","unstructured":"Karthikeyani V, Nagarajan S. Machine learning classification algorithms to recognize chart types in portable document format (pdf) files. Int J Comput Appl. 2012;39(2):1\u20135.","DOI":"10.5120\/4789-6997"},{"key":"1414_CR60","doi-asserted-by":"crossref","unstructured":"Busch A, Boles WW, Sridharan S. Texture for script identification. IEEE Transactions on PAMI 2005.","DOI":"10.1109\/TPAMI.2005.227"},{"key":"1414_CR61","doi-asserted-by":"crossref","unstructured":"Busch A. Multi-font script identification using texture-based features. In: Campilho A, Kamel M (eds) Image analysis and recognition. 2006.","DOI":"10.1007\/11867661_76"},{"key":"1414_CR62","unstructured":"Singhal V, Navin N, Ghosh D. Script-based classification of hand-written text documents in a multilingual environment. In: RIDE-MLIM 2003."},{"key":"1414_CR63","doi-asserted-by":"crossref","unstructured":"Jaeger S, Ma H, Doermann D. Identifying script on word-level with informational confidence. In: ICDAR 2005.","DOI":"10.1109\/ICDAR.2005.134"},{"key":"1414_CR64","doi-asserted-by":"crossref","unstructured":"Pati PB, Ramakrishnan A. Word level multi-script identification. Pattern Recognit Lett. 2008;29(9):1218\u201329.","DOI":"10.1016\/j.patrec.2008.01.027"},{"key":"1414_CR65","unstructured":"Kunte RS, Samuel RDS. On separation of Kannada and English words from a bilingual document employing Gabor features and radial basis function neural network. ICCR 2005."},{"key":"1414_CR66","doi-asserted-by":"crossref","unstructured":"Philip B, Samuel RS. A novel bilingual OCR for printed Malayalam-English text based on Gabor features and dominant singular values. In: ICDIP 2009.","DOI":"10.1109\/ICDIP.2009.50"},{"key":"1414_CR67","doi-asserted-by":"crossref","unstructured":"Rani R, Dhir R, Lehal GS. Script identification of pre-segmented multi-font characters and digits. In: ICDAR 2013.","DOI":"10.1109\/ICDAR.2013.233"},{"key":"1414_CR68","doi-asserted-by":"crossref","unstructured":"Chanda S, Franke K, Pal U. Identification of indic scripts on torn-documents. In: ICDAR 2011.","DOI":"10.1109\/ICDAR.2011.149"},{"key":"1414_CR69","doi-asserted-by":"crossref","unstructured":"Ukil S, Ghosh S, Md Obaidullah S, Santosh KC, Roy K, Das N. Deep learning for word-level handwritten indic script identification. CoRR 2018.","DOI":"10.1007\/978-981-13-8581-0_9"},{"key":"1414_CR70","doi-asserted-by":"crossref","unstructured":"Sharma N, Mandal R, Sharma R, Pal U, Blumenstein M. ICDAR2015 competition on video script identification (CVSI 2015). In: ICDAR 2015.","DOI":"10.1109\/ICDAR.2015.7333950"},{"key":"1414_CR71","doi-asserted-by":"crossref","unstructured":"Singh AK, Mishra A, Dabral P, Jawahar C. A simple and effective solution for script identification in the wild. In: DASW 2016.","DOI":"10.1109\/DAS.2016.57"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01414-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-022-01414-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01414-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T22:14:43Z","timestamp":1673129683000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-022-01414-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,15]]},"references-count":71,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["1414"],"URL":"https:\/\/doi.org\/10.1007\/s42979-022-01414-4","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,15]]},"assertion":[{"value":"13 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does no contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}],"article-number":"5"}}